Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    potential goals

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     تباہ
    0.47
     שלך
    0.44
    <unused531>
    0.43
     तुमसे
    0.43
    甚至是
    0.43
    ⚉
    0.43
     ಅವನ
    0.42
    ходов
    0.42
     αξ
    0.41
     deinem
    0.41
    POSITIVE LOGITS
     Cond
    0.45
    Cond
    0.45
     Potential
    0.45
     Jet
    0.43
     Environment
    0.42
     potential
    0.42
     Public
    0.41
     Deal
    0.40
     Post
    0.39
     Cool
    0.39
    Act Density 0.001%

    No Known Activations